System and Method for Improving an Image Characteristic of Image Frames in a Video Stream
A system and method for improving a video characteristic of a video stream is described. According to various implementations of the invention, a changed region between a later-in-time image frame and an earlier-in-time image frame and an unchanged region between such two image frames are determined. A new improvement to the video characteristic is determined and applied to the changed region of the later-in-time image frame. A prior improvement to the video characteristic that was determined for the earlier-in-time image frame is applied to the unchanged region of the later-in-time image frame.
1 . A method for improving contrast in a plurality of image frames captured by a video camera, the method comprising:
generating, by a computing processor, a first transformation function that improves contrast of a first frame of the plurality of image frames;
applying, by a computing processor, the first transformation function to the first frame to improve the contrast of the first frame;
determining, by a computing processor, a changed region in a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames;
generating a second transformation function corresponding to the changed region of the second frame;
applying the second transformation function to the changed region of the second frame to improve the contrast of the changed region; and
applying the first transformation function to the unchanged region of the first frame to improve the contrast of the unchanged region.
2 . The method of claim 1 , wherein generating a first transformation function that improves contrast of a first frame of the plurality of image frames comprises:
generating a histogram for the first frame.
3 . The method of claim 2 , wherein generating a histogram for the first frame comprises:
generating a plurality of histograms for the first frame, each of the plurality of histograms corresponding to one of a plurality of regions of the first frame.
4 . The method of claim 3 , wherein generating a first transformation function that improves contrast of a first frame of the plurality of image frames comprises:
generating a first plurality of transformation functions, each of the plurality of transformation functions corresponding to one of the plurality of regions of the first frame.
5 . A method for improving contrast of a plurality of image frames in a video stream captured by a video camera, the method comprising:
determining, by a computing processor, a first CLAHE transformation for each of a plurality of regions of an earlier-in-time image frame of the plurality of image frames;
determining, by the computing processor, a changed region of a later-in-time image frame of the plurality of image frames relative to the earlier-in-time image frame and an unchanged region of the later-in-time image frame of the plurality of image frames relative to the earlier-in-time image frame;
determining, by the computing processor, a new CLAHE transformation for the changed region of the later-in-time image frame of the plurality of image frames;
applying, by the computing processor, the first CLAHE transformation to the unchanged region of the later-in-time image frame of the plurality of image frames; and
applying, by the computing processor, the new CLAHE transformation to the changed region of the later-in-time image frame of the plurality of image frames.
6 . A method for improving an image characteristic of a plurality of image frames in a video stream captured by a video camera, the method comprising:
determining, by a computing processor, a first improvement to the image characteristic for a first frame of the plurality of image frames;
determining, by a computing processor, a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames;
determining, by a computing processor, a second improvement to the image characteristic for the changed region of the second frame of the plurality of image frames;
applying, by a computing processor, the first improvement to the image characteristic of the unchanged region of the second frame of the plurality of image frames; and
applying, by a computing processor, the second improvement to the image characteristic of the changed region of the second frame of the plurality of image frames.
7 . The method of claim 6 , wherein determining a first improvement to the image characteristic for a first frame of the plurality of image frames comprises:
generating a first plurality of histograms, each of the first plurality of histograms corresponding to one of a plurality of regions of the first frame of the plurality of image frames.
8 . The method of claim 7 , wherein each of the plurality of regions comprises a plurality of pixels.
9 . The method of claim 7 , wherein determining a first improvement to the image characteristic for a first frame of the plurality of image frames further comprises:
generating a plurality of transformation functions, each of the plurality of transformation functions generated from a corresponding one of the first plurality of histograms and associated with a corresponding one of the plurality of regions of the first frame.
10 . The method of claim 9 , wherein determining a first improvement to the image characteristic for a first frame of the plurality of image frames further comprises:
storing the plurality of transformation functions for the plurality of regions of the first frame as the first improvement.
11 . The method of claim 6 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:
determining a number of pixels in a region of the second frame that exceed a difference threshold relative to corresponding pixels in the first frame in order to determine the changed region.
12 . The method of claim 6 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:
determining a number of pixels in a region of the second frame that differ relative to corresponding pixels in the first frame in order to determine the changed region.
13 . The method of claim 6 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises:
determining a motion of a region in the first frame; and
extrapolating the motion of the region to the second frame.
14 . The method of claim 6 , wherein determining a second improvement to the image characteristic for the changed region of the second frame of the plurality of image frames comprises:
generating a second histogram for the changed region of the second frame.
15 . The method of claim 14 , wherein determining a second improvement to the image characteristic for the changed region of the second frame of the plurality of image frames further comprises:
generating a second transformation function from the second histogram for the changed region of the second frame.
16 . The method of claim 15 , wherein applying the second improvement to the image characteristic of the changed region of the second frame of the plurality of image frames comprises:
applying the second transformation function to the changed region of the second frame.
17 . The method of claim 16 , wherein applying the second transformation function to the changed region of the second frame comprises:
applying the second transformation function to each of a plurality of pixels in the changed region of the second frame.
18 . The method of claim 6 , wherein determining a first improvement to the image characteristic comprises:
determining at least one intermediate computation; and
storing a result of the at least one intermediate computation; and
wherein applying the first improvement to the image characteristic of the unchanged region of the second frame comprises applying the result of the at least one intermediate computation to the image characteristic of the unchanged region of the second frame.
19 . The method of claim 18 , wherein the at least one intermediate computation comprises a computationally expensive intermediate computation.
20 . The method of claim 6 , wherein determining a changed region of a second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames and an unchanged region of the second frame of the plurality of image frames in relation to the first frame of the plurality of the image frames comprises determining that the changed region is due to a change in illumination in the image frame, and
wherein determining a second improvement to the image characteristic for the changed region of the second frame of the plurality of image frames comprises determining the second improvement by scaling or shifting the first improvement.